BIGOS V2: Benchmark for Polish Automatic Speech Recognition Systems

BIGOS (Benchmark Intended Grouping of Open Speech) is a collection of openly available Polish speech corpora. Its goal is to simplify access to these resources and enable systematic benchmarking of open and commercial Polish automatic speech recognition (ASR) systems. The dataset was created by amu-cai and was last updated on 2026-02-18.

Use Cases

• Benchmarking commercial Polish ASR systems based on the described collection of open speech corpora.
• Evaluating open-source Polish speech recognition models against a standardized test suite.
• Training or fine-tuning Polish ASR models using aggregated, openly available speech data.

Strengths

• Explicitly designed for systematic benchmarking of Polish ASR systems, providing a clear purpose.
• Aggregates multiple openly available Polish speech corpora into a single, simplified access point.
• Last updated on 2026-02-18, suggesting potential maintenance.

Limitations

• Description metadata is limited; actual data quality, size, and structure require manual inspection after download.
• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and license information are unknown, which may limit suitability assessment.

Provenance

Source

amu-cai via Hugging Face

Collection Method

Aggregation of openly available Polish speech corpora.

Freshness

Last updated 2026-02-18 21:59:33; freshness should be verified.

Geography

Poland (implied by focus on Polish language)